Skip to content

fix merge error of llmc bug#1817

Open
n1ck-guo wants to merge 2 commits into
mainfrom
hengguo/fix_merge_error_0514
Open

fix merge error of llmc bug#1817
n1ck-guo wants to merge 2 commits into
mainfrom
hengguo/fix_merge_error_0514

Conversation

@n1ck-guo
Copy link
Copy Markdown
Contributor

Description

Please briefly describe your main changes, the motivation.

Type of Change

Bug fix

Related Issues

Fixes or relates to #

Checklist Before Submitting

  • My code has been tested locally.
  • Documentation has been updated as needed.
  • New or updated tests are included where applicable.
  • The CUDA CI has passed. You can trigger it by commenting /azp run Unit-Test-CUDA-AutoRound.

Copilot AI review requested due to automatic review settings May 14, 2026 06:37
@n1ck-guo
Copy link
Copy Markdown
Contributor Author

/azp run Unit-Test-CUDA-AutoRound

Signed-off-by: n1ck-guo <heng.guo@intel.com>
@azure-pipelines
Copy link
Copy Markdown

Azure Pipelines successfully started running 1 pipeline(s).

Copy link
Copy Markdown
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Note

Copilot was unable to run its full agentic suite in this review.

This PR fixes a merge-related bug in DataDrivenCompressor.quantize_block by allowing it to run for MLLM models (while still blocking diffusion), and adds a CPU unit test to prevent regressions.

Changes:

  • Relaxed quantize_block guard to only reject diffusion models (no longer rejects MLLM).
  • Added a CPU test ensuring quantize_block works for MLLM and that is_mllm is restored after preprocessing.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 4 comments.

File Description
test/test_cpu/core/test_llmc_quantize_block.py Adds regression test verifying MLLM is allowed and is_mllm is restored after quantize_block.
auto_round/compressors/data_driven.py Updates model-type guard to reject only diffusion models.

Comment thread auto_round/compressors/data_driven.py Outdated
Comment thread test/test_cpu/core/test_llmc_quantize_block.py
Comment thread test/test_cpu/core/test_llmc_quantize_block.py
Comment thread test/test_cpu/core/test_llmc_quantize_block.py
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants